Job Title: Search Model Specialist
About the Role:
* We are seeking a seasoned engineer with expertise in building scalable search systems and AI models.
Key Responsibilities:
* Work full-time hours on a contract basis (10AM - 6PM BRT)
* Collaborate with our team to develop and optimize RAG models for search across large-scale medical and scientific documents
* Fine-tune LLMs for textual RAG use cases, focusing on semantic chunking strategies and automated evaluation pipeline improvement
Requirements:
* 1+ years of experience as a Search Engineer or AI Engineer
* Strong Python development skills, including API creation, model training, testing, and general backend programming
* Familiarity with LangChain and OpenSearch
Nice to Have Skills:
* Familiarity with AWS infrastructure (IAM, VPC, S3, etc.)
* Exposure to RAG architectures, specifically textual RAG use cases
Project Overview:
We aim to build efficient and accurate search features for an existing Retrieval-Augmented Generation (RAG) service. As a key member of our team, you will leverage your technical expertise to drive innovation and quality in our search solutions.